breaking-change-doc

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads public, user-generated GitHub content as part of its required workflow (Step 1 reads PR bodies, comments, reviews, and closing issues; Step 4 uses gh api to read the dotnet/docs issue template and recent breaking-change issues), so untrusted third-party content is ingested and used to influence documentation generation and subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs a runtime fetch of the breaking-change issue template (gh api repos/dotnet/docs/contents/.github/ISSUE_TEMPLATE/02-breaking-change.yml -H "Accept: application/vnd.github.raw"), and that fetched content is used as a structural reference that directly shapes the generated issue/prompts, so it is a runtime external dependency controlling agent output.